No model found in config file when trying to load converted model about keras

[dchouren]

Not sure if this is relevant, but I tried to do some basic inspection with h5py and have this:

>>> import h5py
>>> x = h5py.File('models/Keras_model_weights.h5', 'r')
>>> [y for y in x]
['conv1_1', 'conv1_1_zeropadding', 'conv1_2', 'conv1_2_zeropadding', 'conv2_1', 'conv2_1_zeropadding', 'conv2_2', 'conv2_2_zeropadding', 'conv3_1', 'conv3_1_zeropadding', 'conv3_2', 'conv3_2_zeropadding', 'conv3_3', 'conv3_3_zeropadding', 'conv4_1', 'conv4_1_zeropadding', 'conv4_2', 'conv4_2_zeropadding', 'conv4_3', 'conv4_3_zeropadding', 'conv5_1', 'conv5_1_zeropadding', 'conv5_2', 'conv5_2_zeropadding', 'conv5_3', 'conv5_3_zeropadding', 'data', 'drop6', 'drop7', 'fc6', 'fc6_flatten', 'fc7', 'fc8a', 'pool1', 'pool2', 'pool3', 'pool4', 'pool5', 'prob', 'relu1_1', 'relu1_2', 'relu2_1', 'relu2_2', 'relu3_1', 'relu3_2', 'relu3_3', 'relu4_1', 'relu4_2', 'relu4_3', 'relu5_1', 'relu5_2', 'relu5_3', 'relu6', 'relu7']

[MarcBS]

Hi @dchouren , are you trying to load the model with the original Keras version? Or with this fork?

[dchouren]

Have tried both with the same result

[dchouren]

@MarcBS So it seems that what's being created is just a weights file. Is that correct? I can create a model, say VGG16, and then use model.load_weights('...') and that works. I would suggest changing the output from
'Finished storing the converted model...'
to indicate that this isn't an .h5 model file but rather just the layer weights so there's no confusion.